Automatic multi-modal meeting camera selection for video-conferences and meeting browsers

Marc Al-Hames, Benedikt Hörnler, Ronald Müller, Joachim Schenk, Gerhard Rigoll

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

10 Zitate (Scopus)

Abstract

In a video-conference the participants usually see the video of the speaker. However if somebody reacts (e. g. nodding) the system should switch to his video. Current systems do not support this. We formulate this camera selection as a pattern recognition problem. Then we apply HMMs to learn this behaviour. Thus our system can easily be adapted to different meeting scenarios. Furthermore, while current systems stay on the speaker, our system will switch if somebody reacts. In an experimental section we show that - compared to a desired output - a current system shows the wrong camera more than half of the time (frame error rate 53%), where our system selects the wrong camera in only a quarter of the time (FER 27%).

OriginalspracheEnglisch
TitelProceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007
Herausgeber (Verlag)IEEE Computer Society
Seiten2074-2077
Seitenumfang4
ISBN (Print)1424410177, 9781424410170
DOIs
PublikationsstatusVeröffentlicht - 2007
VeranstaltungIEEE International Conference onMultimedia and Expo, ICME 2007 - Beijing, China
Dauer: 2 Juli 20075 Juli 2007

Publikationsreihe

NameProceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007

Konferenz

KonferenzIEEE International Conference onMultimedia and Expo, ICME 2007
Land/GebietChina
OrtBeijing
Zeitraum2/07/075/07/07

Fingerprint

Untersuchen Sie die Forschungsthemen von „Automatic multi-modal meeting camera selection for video-conferences and meeting browsers“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren